Related papers: CONA: A novel CONtext-Aware instruction paradigm f…
E-learning environments are increasingly harnessing large language models (LLMs) like GPT-3.5 and GPT-4 for tailored educational support. This study introduces an approach that integrates dynamic knowledge graphs with LLMs to offer nuanced…
Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…
While multi-modal learning has advanced significantly, current approaches often treat modalities separately, creating inconsistencies in representation and reasoning. We introduce MANTA (Multi-modal Abstraction and Normalization via Textual…
Large language models (LLMs) have achieved remarkable performance in various natural language processing tasks, especially in dialogue systems. However, LLM may also pose security and moral threats, especially in multi round conversations…
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…
Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context. The existing works…
In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guided via ICL infer the…
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…
Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intentions and values, improving context-faithfulness through…
Knowledge graphs contain rich semantic relationships related to items and incorporating such semantic relationships into recommender systems helps to explore the latent connections of items, thus improving the accuracy of prediction and…
In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…
Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode context directly into model parameters can effectively enable…
There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained…
While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts.…
Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…
Understanding how large language models (LLMs) acquire, retain, and apply knowledge remains an open challenge. This paper introduces a novel framework, K-(CSA)^2, which categorizes LLM knowledge along two dimensions: correctness and…
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These…
Knowledge-grounded dialogue systems aim to generate coherent and engaging responses based on the dialogue contexts and selected external knowledge. Previous knowledge selection methods tend to rely too heavily on the dialogue contexts or…
Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn…